Method for estimating posture of moving object by using big cell grid map, recording medium in which program for implementing same is stored, and computer program stored in medium in order to implement same

Abstract

Embodiments are proposed, including: a method for estimating the posture of a moving object by using a big cell grid map; a recording medium in which a program for implementing the method is stored; and the computer program stored in the medium to implement the method. More particularly, there are provided the embodiments including: a method for estimating the posture of a moving object by using a big cell grid map, the method dividing a map into a plurality of finite cells, and estimating and correcting the posture of a moving robot in the map (the big cell grid map) where map feature point information about a map feature point corresponding to a position of a corresponding cell is matched for each cell; a recording medium where a program for implementing the method is stored, and the computer program stored in the medium to implement the method.

1 . A method for estimating a pose of a robot travelling in a prescribed area, the method comprising:
 storing first information on a plurality of cells constituting the area and second information on first feature of each of the plurality of cells;   estimating a first pose of the robot based on driving information of the robot, the first pose comprising a position of the robot;   determining third information detected by a sensor of the robot at a current position of the robot, the third information comprising a second feature adjacent to the current position and a distance from the current position to the second feature;   selecting cells corresponding to a region detected by the sensor in the plurality of cells based on the current position of the robot; and   determining a second pose of the robot by modifying the first pose based on a result of comparing the second information of the cell corresponding to the region and the third information.   
     
     
         2 . The method of  claim 1 , wherein the storing comprises:
 dividing the area into the plurality of cells;   determining the first information of each of the plurality of cells, the first information including identification information of each of the plurality of cells;   mapping the first and the second information of the plurality of cells; and   storing the first information and the second information in a memory of the robot.   
     
     
         3 . The method of  claim 2 , wherein the storing further comprises:
 updating and storing the second information when the robot detects that the first feature is changed.   
     
     
         4 . The method of  claim 2 , wherein the second information includes information representing a shape of an object located in the area in a geometric form. 
     
     
         5 . The method of  claim 2 , wherein the second information includes any one of information on obstacles in the area, a moving point registered in advance, or identification for location recognition. 
     
     
         6 . The method of  claim 1 , wherein the estimating includes estimating the first pose of the robot based on the pose immediately before the robot moves and the travelling distance determined by the sensor of the robot. 
     
     
         7 . The method of  claim 1 , wherein the selecting includes selecting the cells corresponding to the region detected by the sensor in the plurality of cells based on the first pose of the robot. 
     
     
         8 . A method for estimating a pose of a robot travelling in a prescribed area, the method comprising:
 storing first information on a plurality of cells constituting the area and second information on first feature of each of the plurality of cells,   determining third information detected by a sensor of the robot at a current position of the robot, the third information comprising a second feature adjacent to the current position and a distance from the current position to the second feature;   selecting cells corresponding to a region detected by the sensor in the plurality of cells based on the current position of the robot; and   determining the pose of the robot based on a result of comparing the second information of the cell corresponding to the region and the third information.   
     
     
         9 . The method of  claim 8 , wherein the storing comprises:
 dividing the area into the plurality of cells;   determining the first information of each of the plurality of cells, the first information including identification information of each of the plurality of cells;   mapping the first and the second information of the plurality of cells; and   storing the first information and the second information in a memory of the robot.   
     
     
         10 . The method of  claim 9 , wherein the storing further comprises:
 updating and storing the second information when the robot detects that the first feature is changed.   
     
     
         11 . The method of  claim 9 , wherein the second information includes information representing a shape of an object located in the area in a geometric form. 
     
     
         12 . The method of  claim 9 , wherein the second information includes any one of information on obstacles in the area, a moving point registered in advance, or identification for location recognition. 
     
     
         13 . A system for estimating a pose of a robot travelling in a prescribed area, the system comprising:
 a memory;   a sensor configured to collect environmental data around the robot; and   one or more processor programmed to:
 store first information on a plurality of cells constituting the area and second information on first feature of each of the plurality of cells in the memory, 
 determine third information detected by the sensor at a current position of the robot, the third information comprising a second feature adjacent to the current position and a distance from the current position to the second feature; 
 select cells corresponding to a region detected by the sensor in the plurality of cells based on the current position of the robot; and 
 determine the first pose of the robot based on a result of comparing the second information of the cell corresponding to the region and the third information. 
   
     
     
         14 . The system of  claim 13 , wherein the processor is further programmed to:
 estimate a second pose of the robot based on driving information of the robot, the second pose comprising a position of the robot.   
     
     
         15 . The system of  claim 14 , wherein the processor is programmed to:
 determine the first pose of the robot by modifying the second pose based on the result of comparing the second information of the cell corresponding to the region and the third information.